Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the APIs do Web Report, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnasajon.app%2Fnasajon" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnasajon.app%2Fnasajon" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with APIs do Web Report API.
Register database connections the report engine will query
Define saved queries that pull the rows a report needs
Configure JSON and database data sources for report layouts
Build and store report layouts that bind data to a template
Run report jobs and poll each job by its id for the finished output
GET STARTED
Retrieve a report job's status and output once rendering completes
Patterns agents use APIs do Web Report API for, with concrete tasks.
★ AI Reporting Agent
An AI agent connected through Jentic produces a business report on request by selecting a saved query and layout, submitting the report job, and polling it until the output is ready, so a user asking for a monthly summary gets a finished document without the developer sequencing the calls by hand. The agent reuses the data sources and layouts already configured in the account.
Submit a report job for the monthly sales layout against its data source, then poll the job id and return the finished output
Scheduled Document Rendering
A back-office product renders recurring documents by storing a layout and query once and triggering a report job on a schedule. Because each job is tracked by its id, the product can fire many renders and collect the outputs asynchronously as they complete rather than blocking on each one.
Trigger report jobs for a list of saved layouts and collect each finished output by polling its job id
Data Source Management
An operations tool wires new reports to live data by registering a database connection, defining a JSON or database data source over it, and binding that source into a report layout. Connections and data sources are addressed by id so a single source can back many layouts and report runs.
Register a database connection, define a data source over it, and bind the source into a new report layout
27 endpoints — the web report api from nasajon generates formatted reports from configured data sources and layouts.
METHOD
PATH
DESCRIPTION
/reports
List report definitions
/reports
Submit a report run
/reports/jobs/{id}
Get a report job's status and output
/consultas
List saved queries
/datasources
List configured data sources
/layouts
List report layouts
/conexoes
List database connections
/reports
List report definitions
/reports
Submit a report run
/reports/jobs/{id}
Get a report job's status and output
/consultas
List saved queries
/datasources
List configured data sources
/layouts
List report layouts
/conexoes
List database connections
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Web Report API by hand means implementing its OAuth2 password flow, managing tokens with the offline_access scope, and sequencing the data-source, layout, and report-job calls yourself. Through Jentic you install once, import it from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Reports read from the sources you connect, so a rule can give the agent just the query and report-generation operations and leave connection and data-source changes out. You choose which operations it may call.
Credential isolation
Your Web Report OAuth2 token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'generate a report' or 'list the saved queries', and Jentic returns the matching Web Report operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using APIs do Web Report API through Jentic.
What authentication does the Web Report API use?
The Web Report API uses OAuth2 with the password flow and an offline_access scope, per its OpenAPI spec, so your client exchanges credentials for a bearer token and refreshes it as needed. Through Jentic that token is held encrypted by your own Jentic One instance and injected at call time.
Can I generate a report with the Web Report API?
Yes. You submit a report request against a configured layout and data source, then poll the report job by its id until the output is ready. Saved queries and data sources are defined once and reused across report runs, so a single request kicks off the render.
Can I manage data sources with the Web Report API?
Yes. The API registers database connections and both JSON and database data sources, which report layouts then bind to. Each data source is addressed by its id so one source can back many layouts and report jobs.
Can I limit what my agent is allowed to do with the Web Report API?
Yes. Write a rule that allows only the query and report-generation operations, so the agent runs and fetches reports while connection, data-source, and layout changes stay out of its reach unless you add them. Every call the agent makes is logged.
How do I generate a report with the Web Report API through Jentic?
Search by intent in Jentic with a query like 'generate a Web Report', add the Web Report API from the Jentic API Directory, and your agent submits the report request then polls the job id for the finished output. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Know of an official OpenAPI document? Contribute it →
For Agents
Define data sources, queries, and layouts, then generate reports and poll each report job for its output. Built around saved connections and reusable report templates.
Use for: Generate a sales report from a saved query, List all report layouts available, Check the status of a report job by its id, Register a new database connection for reporting
Not supported: Does not handle data warehousing, live dashboards, or report email delivery. Use for generating formatted reports from configured data sources only.
The Web Report API from Nasajon generates formatted reports from configured data sources and layouts. It registers database connections, defines JSON and database data sources, stores saved queries and report layouts, then runs report jobs and returns their output by job id. Teams use it to turn structured business data into on-demand report documents.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>